Marco Mondelli

ORCID

Publication Activity (10 Years)

Years Active: 2011-2024
Publications (10 Years): 104

Top Venues

CoRR

ISIT

IEEE Trans. Inf. Theory

NeurIPS

Publications

Amedeo Roberto Esposito, Marco Mondelli
Contraction of Markovian Operators in Orlicz Spaces and Error Bounds for Markov Chain Monte Carlo (Extended Abstract). COLT (2024)
Peter Súkeník, Marco Mondelli, Christoph Lampert
Neural Collapse versus Low-rank Bias: Is Deep Neural Collapse Really Optimal? CoRR (2024)
Amedeo Roberto Esposito, Marco Mondelli
Concentration Without Independence via Information Measures. IEEE Trans. Inf. Theory 70 (6) (2024)
Yihan Zhang, Hong Chang Ji, Ramji Venkataramanan, Marco Mondelli
Spectral Estimators for Structured Generalized Linear Models via Approximate Message Passing (Extended Abstract). COLT (2024)
Francesco Pedrotti, Jan Maas, Marco Mondelli
Improved Convergence of Score-Based Diffusion Models via Prediction-Correction. Trans. Mach. Learn. Res. 2024 (2024)
Al Depope, Marco Mondelli, Matthew R. Robinson
Inference of Genetic Effects via Approximate Message Passing. ICASSP (2024)
Amedeo Roberto Esposito, Marco Mondelli
Contraction of Markovian Operators in Orlicz Spaces and Error Bounds for Markov Chain Monte Carlo. CoRR (2024)
Jean Barbier, Francesco Camilli, Marco Mondelli, Yizhou Xu
Information limits and Thouless-Anderson-Palmer equations for spiked matrix models with structured noise. CoRR (2024)
Daniel Beaglehole, Peter Súkeník, Marco Mondelli, Mikhail Belkin
Average gradient outer product as a mechanism for deep neural collapse. CoRR (2024)
Kevin Kögler, Alexander Shevchenko, Hamed Hassani, Marco Mondelli
Compression of Structured Data with Autoencoders: Provable Benefit of Nonlinearities and Depth. CoRR (2024)
Simone Bombari, Marco Mondelli
Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features. CoRR (2024)
Yihan Zhang, Marco Mondelli
Matrix Denoising with Doubly Heteroscedastic Noise: Fundamental Limits and Optimal Spectral Methods. CoRR (2024)
Simone Bombari, Shayan Kiyani, Marco Mondelli
Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels. ICML (2023)
Yizhou Xu, TianQi Hou, Shansuo Liang, Marco Mondelli
Approximate Message Passing for Multi-Layer Estimation in Rotationally Invariant Models. ITW (2023)
Amedeo Roberto Esposito, Marco Mondelli
Concentration without Independence via Information Measures. ISIT (2023)
Peter Súkeník, Marco Mondelli, Christoph H. Lampert
Deep Neural Collapse Is Provably Optimal for the Deep Unconstrained Features Model. NeurIPS (2023)
Simone Bombari, Marco Mondelli
Stability, Generalization and Privacy: Precise Analysis for Random and NTK Features. CoRR (2023)
Amedeo Roberto Esposito, Marco Mondelli
Concentration without Independence via Information Measures. CoRR (2023)
Teng Fu, Yuhao Liu, Jean Barbier, Marco Mondelli, Shansuo Liang, TianQi Hou
Mismatched estimation of non-symmetric rank-one matrices corrupted by structured noise. CoRR (2023)
Yihan Zhang, Hong Chang Ji, Ramji Venkataramanan, Marco Mondelli
Spectral Estimators for Structured Generalized Linear Models via Approximate Message Passing. CoRR (2023)
Teng Fu, Yuhao Liu, Jean Barbier, Marco Mondelli, Shansuo Liang, TianQi Hou
Mismatched estimation of non-symmetric rank-one matrices corrupted by structured noise. ISIT (2023)
Francesco Pedrotti, Jan Maas, Marco Mondelli
Improved Convergence of Score-Based Diffusion Models via Prediction-Correction. CoRR (2023)
Peter Súkeník, Marco Mondelli, Christoph Lampert
Deep Neural Collapse Is Provably Optimal for the Deep Unconstrained Features Model. CoRR (2023)
Aleksandr Shevchenko, Kevin Kögler, Hamed Hassani, Marco Mondelli
Fundamental Limits of Two-layer Autoencoders, and Achieving Them with Gradient Methods. ICML (2023)
Diyuan Wu, Vyacheslav Kungurtsev, Marco Mondelli
Mean-field analysis for heavy ball methods: Dropout-stability, connectivity, and global convergence. Trans. Mach. Learn. Res. 2023 (2023)
Simone Bombari, Shayan Kiyani, Marco Mondelli
Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels. CoRR (2023)
Jean Barbier, Francesco Camilli, Marco Mondelli, Manuel Sáenz
Bayes-optimal limits in structured PCA, and how to reach them. CoRR (2022)
Massimo Fornasier, Timo Klock, Marco Mondelli, Michael Rauchensteiner
Finite Sample Identification of Wide Shallow Neural Networks with Biases. CoRR (2022)
Ramji Venkataramanan, Kevin Kögler, Marco Mondelli
Estimation in Rotationally Invariant Generalized Linear Models via Approximate Message Passing. ICML (2022)
Simone Bombari, Mohammad Hossein Amani, Marco Mondelli
Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization. CoRR (2022)
Simone Bombari, Mohammad Hossein Amani, Marco Mondelli
Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization. NeurIPS (2022)
Alexander Shevchenko, Vyacheslav Kungurtsev, Marco Mondelli
Mean-field Analysis of Piecewise Linear Solutions for Wide ReLU Networks. J. Mach. Learn. Res. 23 (2022)
Mohammad Hossein Amani, Simone Bombari, Marco Mondelli, Rattana Pukdee, Stefano Rini
Sharp asymptotics on the compression of two-layer neural networks. ITW (2022)
Yihan Zhang, Marco Mondelli, Ramji Venkataramanan
Precise Asymptotics for Spectral Methods in Mixed Generalized Linear Models. CoRR (2022)
Nghia Doan, Seyyed Ali Hashemi, Marco Mondelli, Warren J. Gross
Decoding Reed-Muller Codes With Successive Codeword Permutations. IEEE Trans. Commun. 70 (11) (2022)
Marco Mondelli, Christos Thrampoulidis, Ramji Venkataramanan
Optimal Combination of Linear and Spectral Estimators for Generalized Linear Models. Found. Comput. Math. 22 (5) (2022)
Jean Barbier, Tianqi Hou, Marco Mondelli, Manuel Sáenz
The price of ignorance: how much does it cost to forget noise structure in low-rank matrix estimation? CoRR (2022)
Jean Barbier, TianQi Hou, Marco Mondelli, Manuel Sáenz
The price of ignorance: how much does it cost to forget noise structure in low-rank matrix estimation? NeurIPS (2022)
Alexander Shevchenko, Kevin Kögler, Hamed Hassani, Marco Mondelli
Fundamental Limits of Two-layer Autoencoders, and Achieving Them with Gradient Methods. CoRR (2022)
Diyuan Wu, Vyacheslav Kungurtsev, Marco Mondelli
Mean-field analysis for heavy ball methods: Dropout-stability, connectivity, and global convergence. CoRR (2022)
Mohammad Hossein Amani, Simone Bombari, Marco Mondelli, Rattana Pukdee, Stefano Rini
Sharp asymptotics on the compression of two-layer neural networks. CoRR (2022)
Seyyed Ali Hashemi, Marco Mondelli, Arman Fazeli, Alexander Vardy, John M. Cioffi, Andrea Goldsmith
Parallelism Versus Latency in Simplified Successive-Cancellation Decoding of Polar Codes. IEEE Trans. Wirel. Commun. 21 (6) (2022)
Yizhou Xu, Tianqi Hou, Shansuo Liang, Marco Mondelli
Approximate Message Passing for Multi-Layer Estimation in Rotationally Invariant Models. CoRR (2022)
Dorsa Fathollahi, Marco Mondelli
Polar Coded Computing: The Role of the Scaling Exponent. ISIT (2022)
Dorsa Fathollahi, Marco Mondelli
Polar Coded Computing: The Role of the Scaling Exponent. CoRR (2022)
Seyyed Ali Hashemi, Marco Mondelli, John M. Cioffi, Andrea Goldsmith
Successive Syndrome-Check Decoding of Polar Codes. ACSCC (2021)
Seyyed Ali Hashemi, Marco Mondelli, Arman Fazeli, Alexander Vardy, John M. Cioffi, Andrea Goldsmith
Parallelism versus Latency in Simplified Successive-Cancellation Decoding of Polar Codes. ISIT (2021)
Seyyed Ali Hashemi, Marco Mondelli, John M. Cioffi, Andrea Goldsmith
Successive Syndrome-Check Decoding of Polar Codes. CoRR (2021)
Marco Mondelli, Ramji Venkataramanan
Approximate Message Passing with Spectral Initialization for Generalized Linear Models. AISTATS (2021)
Arman Fazeli, Hamed Hassani, Marco Mondelli, Alexander Vardy
Binary Linear Codes With Optimal Scaling: Polar Codes With Large Kernels. IEEE Trans. Inf. Theory 67 (9) (2021)
Marco Mondelli, Ramji Venkataramanan
PCA Initialization for Approximate Message Passing in Rotationally Invariant Models. CoRR (2021)
Quynh Nguyen, Pierre Bréchet, Marco Mondelli
When Are Solutions Connected in Deep Networks? NeurIPS (2021)
Marco Mondelli, Ramji Venkataramanan
PCA Initialization for Approximate Message Passing in Rotationally Invariant Models. NeurIPS (2021)
Quynh Nguyen, Pierre Bréchet, Marco Mondelli
On Connectivity of Solutions in Deep Learning: The Role of Over-parameterization and Feature Quality. CoRR (2021)
Alexander Shevchenko, Vyacheslav Kungurtsev, Marco Mondelli
Mean-field Analysis of Piecewise Linear Solutions for Wide ReLU Networks. CoRR (2021)
Quynh Nguyen, Marco Mondelli, Guido F. Montúfar
Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks. ICML (2021)
Nghia Doan, Seyyed Ali Hashemi, Marco Mondelli, Warren J. Gross
Decoding Reed-Muller Codes with Successive Factor-Graph Permutations. CoRR (2021)
Dorsa Fathollahi, Nariman Farsad, Seyyed Ali Hashemi, Marco Mondelli
Sparse Multi-Decoder Recursive Projection Aggregation for Reed-Muller Codes. ISIT (2021)
Ramji Venkataramanan, Kevin Kögler, Marco Mondelli
Estimation in Rotationally Invariant Generalized Linear Models via Approximate Message Passing. CoRR (2021)
Marco Mondelli, Seyyed Ali Hashemi, John M. Cioffi, Andrea Goldsmith
Sublinear Latency for Simplified Successive Cancellation Decoding of Polar Codes. IEEE Trans. Wirel. Commun. 20 (1) (2021)
Quynh Nguyen, Marco Mondelli, Guido Montúfar
Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks. CoRR (2020)
Alexander Shevchenko, Marco Mondelli
Landscape Connectivity and Dropout Stability of SGD Solutions for Over-parameterized Neural Networks. ICML (2020)
Quynh Nguyen, Marco Mondelli
Global Convergence of Deep Networks with One Wide Layer Followed by Pyramidal Topology. NeurIPS (2020)
Marco Mondelli, Christos Thrampoulidis, Ramji Venkataramanan
Optimal Combination of Linear and Spectral Estimators for Generalized Linear Models. CoRR (2020)
Seyyed Ali Hashemi, Marco Mondelli, Arman Fazeli, Alexander Vardy, John M. Cioffi, Andrea Goldsmith
Parallelism versus Latency in Simplified Successive-Cancellation Decoding of Polar Codes. CoRR (2020)
Marco Mondelli, Ramji Venkataramanan
Approximate Message Passing with Spectral Initialization for Generalized Linear Models. CoRR (2020)
Marco Mondelli, Seyyed Ali Hashemi, John M. Cioffi, Andrea Goldsmith
Simplified Successive Cancellation Decoding of Polar Codes Has Sublinear Latency. ISIT (2020)
Dorsa Fathollahi, Nariman Farsad, Seyyed Ali Hashemi, Marco Mondelli
Sparse Multi-Decoder Recursive Projection Aggregation for Reed-Muller Codes. CoRR (2020)
Quynh Nguyen, Marco Mondelli
Global Convergence of Deep Networks with One Wide Layer Followed by Pyramidal Topology. CoRR (2020)
Alexander Shevchenko, Marco Mondelli
Landscape Connectivity and Dropout Stability of SGD Solutions for Over-parameterized Neural Networks. CoRR (2019)
Seyyed Ali Hashemi, Carlo Condo, Marco Mondelli, Warren J. Gross
Rate-Flexible Fast Polar Decoders. IEEE Trans. Signal Process. 67 (22) (2019)
Marco Mondelli, Andrea Montanari
On the Connection Between Learning Two-Layer Neural Networks and Tensor Decomposition. AISTATS (2019)
Seyyed Ali Hashemi, Carlo Condo, Marco Mondelli, Warren J. Gross
Rate-Flexible Fast Polar Decoders. CoRR (2019)
Seyyed Ali Hashemi, Carlo Condo, Marco Mondelli, Warren J. Gross
Rate-Flexible Fast Polar Decoders. ITW (2019)
Marco Mondelli, S. Hamed Hassani, Rüdiger L. Urbanke
A New Coding Paradigm for the Primitive Relay Channel. Algorithms 12 (10) (2019)
Marco Mondelli, Seyyed Ali Hashemi, John M. Cioffi, Andrea Goldsmith
Sublinear Latency for Simplified Successive Cancellation Decoding of Polar Codes. CoRR (2019)
Adel Javanmard, Marco Mondelli, Andrea Montanari
Analysis of a Two-Layer Neural Network via Displacement Convexity. CoRR (2019)
Marco Mondelli, S. Hamed Hassani, Rüdiger L. Urbanke
Construction of Polar Codes With Sublinear Complexity. IEEE Trans. Inf. Theory 65 (5) (2019)
Marco Mondelli, Andrea Montanari
Fundamental Limits of Weak Recovery with Applications to Phase Retrieval. Found. Comput. Math. 19 (3) (2019)
Arman Fazeli, S. Hamed Hassani, Marco Mondelli, Alexander Vardy
Binary Linear Codes with Optimal Scaling: Polar Codes with Large Kernels. ITW (2018)
Nghia Doan, Seyyed Ali Hashemi, Marco Mondelli, Warren J. Gross
On the Decoding of Polar Codes on Permuted Factor Graphs. CoRR (2018)
Marco Mondelli, S. Hamed Hassani, Rüdiger L. Urbanke
A New Coding Paradigm for the Primitive Relay Channel. ISIT (2018)
Marco Mondelli, S. Hamed Hassani, Rüdiger L. Urbanke
How to Achieve the Capacity of Asymmetric Channels. IEEE Trans. Inf. Theory 64 (5) (2018)
Nghia Doan, Seyyed Ali Hashemi, Marco Mondelli, Warren J. Gross
On the Decoding of Polar Codes on Permuted Factor Graphs. GLOBECOM (2018)
Marco Mondelli, Andrea Montanari
Fundamental Limits of Weak Recovery with Applications to Phase Retrieval. COLT (2018)
Marco Mondelli, S. Hamed Hassani, Rüdiger L. Urbanke
A New Coding Paradigm for the Primitive Relay Channel. CoRR (2018)
Seyyed Ali Hashemi, Nghia Doan, Marco Mondelli, Warren J. Gross
Decoding Reed-Muller and Polar Codes by Successive Factor Graph Permutations. ISTC (2018)
Marco Mondelli, Andrea Montanari
On the Connection Between Learning Two-Layers Neural Networks and Tensor Decomposition. CoRR (2018)
Seyyed Ali Hashemi, Marco Mondelli, S. Hamed Hassani, Carlo Condo, Rüdiger L. Urbanke, Warren J. Gross
Decoder Partitioning: Towards Practical List Decoding of Polar Codes. IEEE Trans. Commun. 66 (9) (2018)
Seyyed Ali Hashemi, Nghia Doan, Marco Mondelli, Warren J. Gross
Decoding Reed-Muller and Polar Codes by Successive Factor Graph Permutations. CoRR (2018)
Marco Mondelli, Andrea Montanari
Fundamental Limits of Weak Recovery with Applications to Phase Retrieval. CoRR (2017)
Arman Fazeli, S. Hamed Hassani, Marco Mondelli, Alexander Vardy
Binary Linear Codes with Optimal Scaling and Quasi-Linear Complexity. CoRR (2017)
Marco Mondelli, S. Hamed Hassani, Rüdiger L. Urbanke
Construction of polar codes with sublinear complexity. ISIT (2017)
Seyyed Ali Hashemi, Marco Mondelli, S. Hamed Hassani, Rüdiger L. Urbanke, Warren J. Gross
Partitioned List Decoding of Polar Codes: Analysis and Improvement of Finite Length Performance. GLOBECOM (2017)
Marco Mondelli, S. Hamed Hassani, Ivana Maric, Dennis Hui, Song-Nam Hong
Capacity-Achieving Rate-Compatible Polar Codes for General Channels. WCNC Workshops (2017)
Shrinivas Kudekar, Santhosh Kumar, Marco Mondelli, Henry D. Pfister, Eren Sasoglu, Rüdiger L. Urbanke
Reed-Muller Codes Achieve Capacity on Erasure Channels. IEEE Trans. Inf. Theory 63 (7) (2017)
Seyyed Ali Hashemi, Marco Mondelli, S. Hamed Hassani, Rüdiger L. Urbanke, Warren J. Gross
Partitioned List Decoding of Polar Codes: Analysis and Improvement of Finite Length Performance. CoRR (2017)
Shrinivas Kudekar, Santhosh Kumar, Marco Mondelli, Henry D. Pfister, Eren Sasoglu, Rüdiger L. Urbanke
Reed-Muller codes achieve capacity on erasure channels. STOC (2016)
Shrinivas Kudekar, Santhosh Kumar, Marco Mondelli, Henry D. Pfister, Rüdiger L. Urbanke
Comparing the Bit-MAP and Block-MAP Decoding Thresholds of Reed-Muller Codes on BMS Channels. CoRR (2016)
Marco Mondelli, S. Hamed Hassani, Rüdiger L. Urbanke
Unified Scaling of Polar Codes: Error Exponent, Scaling Exponent, Moderate Deviations, and Error Floors. IEEE Trans. Inf. Theory 62 (12) (2016)

Marco Mondelli.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Marco Mondelli